In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation
criteria have been developed within the research field of explainable artificial intelligence …

The unprecedented growth of computational capabilities in recent years has allowed
Artificial Intelligence (AI) models to be developed for medical applications with remarkable …

Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated
applications, but the outcomes of many AI models are challenging to comprehend and trust …

Despite significant progress in the past few years, machine learning systems are still often
viewed as" black boxes", which lack the ability to explain their output decisions. In high …

Counterfactual explanations have shown promising results as a post-hoc framework to make
image classifiers more explainable. In this paper, we propose DiME, a method allowing the …

Using deep learning models to diagnose cancer from histology data presents several
challenges. Cancer grading and localization of regions of interest (ROIs) in these images …

This paper presents a new efficient black-box attribution method built on Hilbert-Schmidt
Independence Criterion (HSIC). Based on Reproducing Kernel Hilbert Spaces (RKHS) …

Despite the great progress of person re-identification (ReID) with the adoption of
Convolutional Neural Networks, current ReID models are opaque and only outputs a scalar …

Weakly-supervised learning (WSL) has recently triggered substantial interest as it mitigates
the lack of pixel-wise annotations. Given global image labels, WSL methods yield pixel-level …

Significant progress has been achieved on the improvement and downstream usages of the
Contrastive Language-Image Pre-training (CLIP) vision-language model, while less …